Ollama v0.40.12新增支持Liquid AI的LFM3与d1模型
AI 总结
Ollama v0.40.12新增支持Liquid AI的LFM3系列和2B d1决策模型。发布说明称，lfm3是一款拥有256K token上下文的1.7B文本模型，lfm3-vl增加图像理解功能，lfm3-audio支持18种语言的语音识别、翻译和文字转语音，lfm3-omni则整合文本、图像和音频。d1模型可对文本和图像作出决策，d1-omni增加了音频支持。发布说明指出，lfm3和d1 2b目前支持Apple硬件，Linux和Windows支持即将推出。
深度见解
发布说明将这些模型定位为适用于本地智能体、工具调用、结构化输出和多模态工作负载，并通过Ollama在Apple硬件上提供LFM3和d1模型系列。
Liquid AI LFM3
LFM3 is Liquid AI's new family of small models built for local agents, tool calling, and structured output, on Liquid's new tri-hybrid architecture. The family includes:
- lfm3: a 1.7B text model with a 256K-token context window
- lfm3-vl: adds image understanding
- lfm3-audio: speech recognition, translation, and text-to-speech in 18 languages
- lfm3-omni: text, images, and audio in one model
ollama run lfm3d1 decision models
Liquid AI's d1 models now come in a 2B size, built on LFM3. d1 makes decisions about text and images, and d1-omni adds audio.
#Ollama#Liquid AI#LFM3#lfm3-vl#lfm3-audio#lfm3-omni#d1#d1-omni